超级分辨率


class   cv::superres::BroxOpticalFlow
 
class   cv::superres::DenseOpticalFlowExt
 
class   cv::superres::DualTVL1OpticalFlow
 
class   cv::superres::FarnebackOpticalFlow
 
class   cv::superres::FrameSource
 
class   cv::superres::PyrLKOpticalFlow
 
class   cv::superres::SuperResolution
  Base class for Super Resolution algorithms. 更多...
 

函数

Ptr < FrameSource cv::superres::createFrameSource_Camera (int deviceId=0)
 
Ptr < FrameSource cv::superres::createFrameSource_Empty ()
 
Ptr < FrameSource cv::superres::createFrameSource_Video (const String &fileName)
 
Ptr < FrameSource cv::superres::createFrameSource_Video_CUDA (const String &fileName)
 
Ptr < BroxOpticalFlow cv::superres::createOptFlow_Brox_CUDA ()
 
Ptr < DualTVL1OpticalFlow cv::superres::createOptFlow_DualTVL1 ()
 
Ptr < DualTVL1OpticalFlow cv::superres::createOptFlow_DualTVL1_CUDA ()
 
Ptr < FarnebackOpticalFlow cv::superres::createOptFlow_Farneback ()
 
Ptr < FarnebackOpticalFlow cv::superres::createOptFlow_Farneback_CUDA ()
 
Ptr < PyrLKOpticalFlow cv::superres::createOptFlow_PyrLK_CUDA ()
 
Ptr < SuperResolution cv::superres::createSuperResolution_BTVL1 ()
  Create Bilateral TV-L1 Super Resolution. 更多...
 
Ptr < SuperResolution cv::superres::createSuperResolution_BTVL1_CUDA ()
 

详细描述

The Super Resolution module contains a set of functions and classes that can be used to solve the problem of resolution enhancement. There are a few methods implemented, most of them are described in the papers [63] and [164] .

函数文档编制

◆  createFrameSource_Camera()

Ptr < FrameSource > cv::superres::createFrameSource_Camera ( int  deviceId = 0 )

◆  createFrameSource_Empty()

Ptr < FrameSource > cv::superres::createFrameSource_Empty ( )

◆  createFrameSource_Video()

Ptr < FrameSource > cv::superres::createFrameSource_Video ( const String fileName )

◆  createFrameSource_Video_CUDA()

Ptr < FrameSource > cv::superres::createFrameSource_Video_CUDA ( const String fileName )

◆  createOptFlow_Brox_CUDA()

Ptr < BroxOpticalFlow > cv::superres::createOptFlow_Brox_CUDA ( )

◆  createOptFlow_DualTVL1()

Ptr < DualTVL1OpticalFlow > cv::superres::createOptFlow_DualTVL1 ( )

◆  createOptFlow_DualTVL1_CUDA()

Ptr < DualTVL1OpticalFlow > cv::superres::createOptFlow_DualTVL1_CUDA ( )

◆  createOptFlow_Farneback()

Ptr < FarnebackOpticalFlow > cv::superres::createOptFlow_Farneback ( )

◆  createOptFlow_Farneback_CUDA()

Ptr < FarnebackOpticalFlow > cv::superres::createOptFlow_Farneback_CUDA ( )

◆  createOptFlow_PyrLK_CUDA()

Ptr < PyrLKOpticalFlow > cv::superres::createOptFlow_PyrLK_CUDA ( )

◆  createSuperResolution_BTVL1()

Ptr < SuperResolution > cv::superres::createSuperResolution_BTVL1 ( )

#include < opencv2/superres.hpp >

Create Bilateral TV-L1 Super Resolution.

This class implements Super Resolution algorithm described in the papers [63] and [164] .

Here are important members of the class that control the algorithm, which you can set after constructing the class instance:

  • int scale Scale factor.
  • int iterations Iteration count.
  • double tau Asymptotic value of steepest descent method.
  • double lambda Weight parameter to balance data term and smoothness term.
  • double alpha Parameter of spacial distribution in Bilateral-TV.
  • int btvKernelSize Kernel size of Bilateral-TV filter.
  • int blurKernelSize Gaussian blur kernel size.
  • double blurSigma Gaussian blur sigma.
  • int temporalAreaRadius Radius of the temporal search area.
  • Ptr< DenseOpticalFlowExt > opticalFlow Dense optical flow algorithm.

◆  createSuperResolution_BTVL1_CUDA()

Ptr < SuperResolution > cv::superres::createSuperResolution_BTVL1_CUDA ( )